Segment, Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way

It is challenging to accurately detect camouflaged objects from their highly similar surroundings. Existing methods mainly leverage a single-stage detection fashion, while neglecting small objects with low-resolution fine edges requires more operations than the larger ones. To tackle camouflaged obj...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 4703 - 4712
Main Authors: Jia, Qi, Yao, Shuilian, Liu, Yu, Fan, Xin, Liu, Risheng, Luo, Zhongxuan
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2022
Subjects:
categorization
Codes
Computer vision
grouping and shape analysis
Image edge detection
Image segmentation
Measurement
Network architecture
Object detection
Recognition: detection
retrieval; Deep learning architectures and techniques; Segmentation
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is challenging to accurately detect camouflaged objects from their highly similar surroundings. Existing methods mainly leverage a single-stage detection fashion, while neglecting small objects with low-resolution fine edges requires more operations than the larger ones. To tackle camouflaged object detection (COD), we are inspired by humans attention coupled with the coarse-to-fine detection strategy, and thereby propose an iterative refinement framework, coined SegMaR, which integrates Segment, Magnify and Reiterate in a multi-stage detection fashion. Specifically, we design a new discriminative mask which makes the model attend on the fixation and edge regions. In addition, we leverage an attention-based sampler to magnify the object region progressively with no need of enlarging the image size. Extensive experiments show our SegMaR achieves remarkable and consistent improvements over other state-of-the-art methods. Especially, we surpass two competitive methods 7.4% and 20.0% respectively in average over standard evaluation metrics on small camouflaged objects. Additional studies provide more promising insights into Seg-MaR, including its effectiveness on the discriminative mask and its generalization to other network architectures. Code is available at https://github.com/dlut-dimt/SegMaR.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.00467